Create Feature Catalog

Build the feature catalog — the highest-value artifact for agents. Budget significant exploration; use repo-explorer for the heavy reading.

Method

1. Start from user-visible surfaces: routes, UI entry points, CLI commands, public

APIs. Each surface is a candidate feature.

1. For each feature, trace the touch list across layers: UI, backend/services,

persistence (tables/collections/files), and tests that exercise it.

1. Cluster and name features the way a USER would name them, not by module names.

Output — ai/analysis/FEATURE_CATALOG.md

For every feature: name · business goal (one line) · touch list per layer · verifying tests · related features. End with two sections agents use most:

• "Where new code lives" — a decision tree from feature-type to target directories.
• The 3-file rule — for each feature, the 3 files to read first to understand it.

Rules

• Every entry [inferred]. Where a layer can't be confirmed, write "UNSURE".
• Do not modify source. Update ai/guide/FEATURE_MAP.md candidate list to reference

the catalog, nothing more.

• Print a sampling guide at the end: the 5 entries a human should spot-check first

(pick the ones you are least sure of).

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: kunalsuri
• Source: kunalsuri/ai-fication-kit
• License: Apache-2.0

Install and usage instructions live in the source repository linked above.